Add new YOLO Data Augmentation guide (ultralytics#20124)

Co-authored-by: UltralyticsAssistant <[email protected]>
Co-authored-by: Glenn Jocher <[email protected]>
Co-authored-by: Ultralytics Assistant <[email protected]>
Co-authored-by: fatih akyon <[email protected]>

Author: 4 people

docs/en/datasets/explorer/explorer.md

@@ -15,7 +15,7 @@ keywords: Ultralytics Explorer, data exploration, semantic search, vector simila
 <a href="https://docs.ultralytics.com/ru">Русский</a> |
 <a href="https://docs.ultralytics.com/de">Deutsch</a> |
 <a href="https://docs.ultralytics.com/fr">Français</a> |
-<a href="https://docs.ultralytics.com/es/">Español</a> |
+<a href="https://docs.ultralytics.com/es">Español</a> |
 <a href="https://docs.ultralytics.com/pt">Português</a> |
 <a href="https://docs.ultralytics.com/tr">Türkçe</a> |
 <a href="https://docs.ultralytics.com/vi">Tiếng Việt</a> |

docs/en/guides/conda-quickstart.md

@@ -28,7 +28,7 @@ This guide provides a comprehensive introduction to setting up a Conda environme
 
 ## Prerequisites
 
-- You should have Anaconda or Miniconda installed on your system. If not, download and install it from [Anaconda](https://www.anaconda.com/) or [Miniconda](https://docs.conda.io/projects/miniconda/en/latest/).
+- You should have Anaconda or Miniconda installed on your system. If not, download and install it from [Anaconda](https://www.anaconda.com/) or [Miniconda](https://www.anaconda.com/docs/main).
 
 ---
 

docs/en/guides/docker-quickstart.md

@@ -80,7 +80,7 @@ Ultralytics offers several Docker images optimized for various platforms and use
 - **Dockerfile-jetson-jetpack6:** Optimized for [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson/) devices running [NVIDIA JetPack 6](https://developer.nvidia.com/embedded/jetpack-sdk-61).
 - **Dockerfile-jupyter:** For interactive development using JupyterLab in the browser.
 - **Dockerfile-python:** Minimal Python environment for lightweight applications.
-- **Dockerfile-conda:** Includes [Miniconda3](https://docs.conda.io/projects/miniconda/en/latest/) and Ultralytics package installed via Conda.
+- **Dockerfile-conda:** Includes [Miniconda3](https://www.anaconda.com/docs/main) and Ultralytics package installed via Conda.
 
 To pull the latest image:
 

docs/en/guides/index.md

@@ -28,6 +28,7 @@ Here's a compilation of in-depth guides to help you master different aspects of
 - [YOLO Common Issues](yolo-common-issues.md) ⭐ RECOMMENDED: Practical solutions and troubleshooting tips to the most frequently encountered issues when working with Ultralytics YOLO models.
 - [YOLO Performance Metrics](yolo-performance-metrics.md) ⭐ ESSENTIAL: Understand the key metrics like mAP, IoU, and [F1 score](https://www.ultralytics.com/glossary/f1-score) used to evaluate the performance of your YOLO models. Includes practical examples and tips on how to improve detection accuracy and speed.
 - [YOLO Thread-Safe Inference](yolo-thread-safe-inference.md) 🚀 NEW: Guidelines for performing inference with YOLO models in a thread-safe manner. Learn the importance of thread safety and best practices to prevent race conditions and ensure consistent predictions.
+- [YOLO Data Augmentation](yolo-data-augmentation.md) 🚀 NEW: Master the complete range of data augmentation techniques in YOLO, from basic transformations to advanced strategies for improving model robustness and performance.
 - [Model Deployment Options](model-deployment-options.md): Overview of YOLO [model deployment](https://www.ultralytics.com/glossary/model-deployment) formats like ONNX, OpenVINO, and TensorRT, with pros and cons for each to inform your deployment strategy.
 - [K-Fold Cross Validation](kfold-cross-validation.md) 🚀 NEW: Learn how to improve model generalization using K-Fold cross-validation technique.
 - [Hyperparameter Tuning](hyperparameter-tuning.md) 🚀 NEW: Discover how to optimize your YOLO models by fine-tuning hyperparameters using the Tuner class and genetic evolution algorithms.

docs/en/guides/nvidia-jetson.md

@@ -550,7 +550,7 @@ The below table represents the benchmark results for five different models (YOLO
 
     Benchmarked with Ultralytics {{ benchmark_version }}
 
-[Explore more benchmarking efforts by Seeed Studio](https://www.seeedstudio.com/blog/2023/03/30/yolov8-performance-benchmarks-on-nvidia-jetson-devices) running on different versions of NVIDIA Jetson hardware.
+[Explore more benchmarking efforts by Seeed Studio](https://www.seeedstudio.com/blog/2023/03/30/yolov8-performance-benchmarks-on-nvidia-jetson-devices/) running on different versions of NVIDIA Jetson hardware.
 
 ## Reproduce Our Results
 

docs/en/guides/yolo-data-augmentation.md

@@ -12,7 +12,7 @@ keywords: Ultralytics, YOLO, YOLO11, object detection, image segmentation, deep
 <a href="https://docs.ultralytics.com/ru">Русский</a> |
 <a href="https://docs.ultralytics.com/de">Deutsch</a> |
 <a href="https://docs.ultralytics.com/fr">Français</a> |
-<a href="https://docs.ultralytics.com/es/">Español</a> |
+<a href="https://docs.ultralytics.com/es">Español</a> |
 <a href="https://docs.ultralytics.com/pt">Português</a> |
 <a href="https://docs.ultralytics.com/tr">Türkçe</a> |
 <a href="https://docs.ultralytics.com/vi">Tiếng Việt</a> |

docs/en/index.md

@@ -1,20 +1,19 @@
-| Argument          | Type    | Default         | Range         | Description                                                                                                                                                               |
-| ----------------- | ------- | --------------- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `hsv_h`           | `float` | `0.015`         | `0.0 - 1.0`   | Adjusts the hue of the image by a fraction of the color wheel, introducing color variability. Helps the model generalize across different lighting conditions.            |
-| `hsv_s`           | `float` | `0.7`           | `0.0 - 1.0`   | Alters the saturation of the image by a fraction, affecting the intensity of colors. Useful for simulating different environmental conditions.                            |
-| `hsv_v`           | `float` | `0.4`           | `0.0 - 1.0`   | Modifies the value (brightness) of the image by a fraction, helping the model to perform well under various lighting conditions.                                          |
-| `degrees`         | `float` | `0.0`           | `-180 - +180` | Rotates the image randomly within the specified degree range, improving the model's ability to recognize objects at various orientations.                                 |
-| `translate`       | `float` | `0.1`           | `0.0 - 1.0`   | Translates the image horizontally and vertically by a fraction of the image size, aiding in learning to detect partially visible objects.                                 |
-| `scale`           | `float` | `0.5`           | `>=0.0`       | Scales the image by a gain factor, simulating objects at different distances from the camera.                                                                             |
-| `shear`           | `float` | `0.0`           | `-180 - +180` | Shears the image by a specified degree, mimicking the effect of objects being viewed from different angles.                                                               |
-| `perspective`     | `float` | `0.0`           | `0.0 - 0.001` | Applies a random perspective transformation to the image, enhancing the model's ability to understand objects in 3D space.                                                |
-| `flipud`          | `float` | `0.0`           | `0.0 - 1.0`   | Flips the image upside down with the specified probability, increasing the data variability without affecting the object's characteristics.                               |
-| `fliplr`          | `float` | `0.5`           | `0.0 - 1.0`   | Flips the image left to right with the specified probability, useful for learning symmetrical objects and increasing dataset diversity.                                   |
-| `bgr`             | `float` | `0.0`           | `0.0 - 1.0`   | Flips the image channels from RGB to BGR with the specified probability, useful for increasing robustness to incorrect channel ordering.                                  |
-| `mosaic`          | `float` | `1.0`           | `0.0 - 1.0`   | Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding.                |
-| `mixup`           | `float` | `0.0`           | `0.0 - 1.0`   | Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability.             |
-| `copy_paste`      | `float` | `0.0`           | `0.0 - 1.0`   | Copies and pastes objects across images, useful for increasing object instances and learning object occlusion. Requires segmentation labels.                              |
-| `copy_paste_mode` | `str`   | `'flip'`        | -             | Copy-Paste augmentation method selection among the options of (`"flip"`, `"mixup"`).                                                                                      |
-| `auto_augment`    | `str`   | `'randaugment'` | -             | Automatically applies a predefined augmentation policy (`randaugment`, `autoaugment`, `augmix`), optimizing for classification tasks by diversifying the visual features. |
-| `erasing`         | `float` | `0.4`           | `0.0 - 0.9`   | Randomly erases a portion of the image during classification training, encouraging the model to focus on less obvious features for recognition.                           |
-| `crop_fraction`   | `float` | `1.0`           | `0.1 - 1.0`   | Crops the classification image to a fraction of its size to emphasize central features and adapt to object scales, reducing background distractions.                      |
+| Argument                                                                                  | Type    | Default         | Range         | Description                                                                                                                                                              |
+| ----------------------------------------------------------------------------------------- | ------- | --------------- | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| [`hsv_h`](../guides/yolo-data-augmentation.md/#hue-adjustment-hsv_h)                      | `float` | `0.015`         | `0.0 - 1.0`   | Adjusts the hue of the image by a fraction of the color wheel, introducing color variability. Helps the model generalize across different lighting conditions.           |
+| [`hsv_s`](../guides/yolo-data-augmentation.md/#saturation-adjustment-hsv_s)               | `float` | `0.7`           | `0.0 - 1.0`   | Alters the saturation of the image by a fraction, affecting the intensity of colors. Useful for simulating different environmental conditions.                           |
+| [`hsv_v`](../guides/yolo-data-augmentation.md/#brightness-adjustment-hsv_v)               | `float` | `0.4`           | `0.0 - 1.0`   | Modifies the value (brightness) of the image by a fraction, helping the model to perform well under various lighting conditions.                                         |
+| [`degrees`](../guides/yolo-data-augmentation.md//#rotation-degrees)                       | `float` | `0.0`           | `0.0 - 180`   | Rotates the image randomly within the specified degree range, improving the model's ability to recognize objects at various orientations.                                |
+| [`translate`](../guides/yolo-data-augmentation.md/#translation-translate)                 | `float` | `0.1`           | `0.0 - 1.0`   | Translates the image horizontally and vertically by a fraction of the image size, aiding in learning to detect partially visible objects.                                |
+| [`scale`](../guides/yolo-data-augmentation.md/#scale-scale)                               | `float` | `0.5`           | `>=0.0`       | Scales the image by a gain factor, simulating objects at different distances from the camera.                                                                            |
+| [`shear`](../guides/yolo-data-augmentation.md/#shear-shear)                               | `float` | `0.0`           | `-180 - +180` | Shears the image by a specified degree, mimicking the effect of objects being viewed from different angles.                                                              |
+| [`perspective`](../guides/yolo-data-augmentation.md/#perspective-perspective)             | `float` | `0.0`           | `0.0 - 0.001` | Applies a random perspective transformation to the image, enhancing the model's ability to understand objects in 3D space.                                               |
+| [`flipud`](../guides/yolo-data-augmentation.md/#flip-up-down-flipud)                      | `float` | `0.0`           | `0.0 - 1.0`   | Flips the image upside down with the specified probability, increasing the data variability without affecting the object's characteristics.                              |
+| [`fliplr`](../guides/yolo-data-augmentation.md/#flip-left-right-fliplr)                   | `float` | `0.5`           | `0.0 - 1.0`   | Flips the image left to right with the specified probability, useful for learning symmetrical objects and increasing dataset diversity.                                  |
+| [`bgr`](../guides/yolo-data-augmentation.md/#bgr-channel-swap-bgr)                        | `float` | `0.0`           | `0.0 - 1.0`   | Flips the image channels from RGB to BGR with the specified probability, useful for increasing robustness to incorrect channel ordering.                                 |
+| [`mosaic`](../guides/yolo-data-augmentation.md/#mosaic-mosaic)                            | `float` | `1.0`           | `0.0 - 1.0`   | Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding.               |
+| [`mixup`](../guides/yolo-data-augmentation.md/#mixup-mixup)                               | `float` | `0.0`           | `0.0 - 1.0`   | Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability.            |
+| [`copy_paste`](../guides/yolo-data-augmentation.md/#copy-paste-copy_paste)                | `float` | `0.0`           | `0.0 - 1.0`   | _Segmentation only_. Copies and pastes objects across images to increase object instances.                                                                               |
+| [`copy_paste_mode`](../guides/yolo-data-augmentation.md/#copy-paste-mode-copy_paste_mode) | `str`   | `'flip'`        | -             | _Segmentation only_. Specifies the `copy-paste` strategy to use. Options include `'flip'` and `'mixup'`.                                                                 |
+| [`auto_augment`](../guides/yolo-data-augmentation.md/#auto-augment-auto_augment)          | `str`   | `'randaugment'` | -             | _Classification only_. Applies a predefined augmentation policy (`'randaugment'`, `'autoaugment'`, or `'augmix'`) to enhance model performance through visual diversity. |
+| [`erasing`](../guides/yolo-data-augmentation.md/#random-erasing-erasing)                  | `float` | `0.4`           | `0.0 - 0.9`   | _Classification only_. Randomly erases regions of the image during training to encourage the model to focus on less obvious features.                                    |

docs/en/macros/augmentation-args.md

@@ -66,7 +66,7 @@ Ultralytics offers a variety of installation methods, including pip, conda, and
 
         ### Conda Docker Image
 
-        Ultralytics Conda Docker images are also available from [DockerHub](https://hub.docker.com/r/ultralytics/ultralytics). These images are based on [Miniconda3](https://docs.conda.io/projects/miniconda/en/latest/) and provide a straightforward way to start using `ultralytics` in a Conda environment.
+        Ultralytics Conda Docker images are also available from [DockerHub](https://hub.docker.com/r/ultralytics/ultralytics). These images are based on [Miniconda3](https://www.anaconda.com/docs/main) and provide a straightforward way to start using `ultralytics` in a Conda environment.
 
         ```bash
         # Set image name as a variable

docs/en/quickstart.md

@@ -16,6 +16,9 @@
 [email protected]:
   avatar: https://avatars.githubusercontent.com/u/131261051?v=4
   username: MatthewNoyce
+[email protected]:
+  avatar: https://avatars.githubusercontent.com/u/132259399?v=4
+  username: picsalex
 [email protected]:
   avatar: https://avatars.githubusercontent.com/u/135830346?v=4
   username: UltralyticsAssistant

docs/mkdocs_github_authors.yaml

@@ -347,6 +347,7 @@ nav:
       - YOLO Common Issues: guides/yolo-common-issues.md
       - YOLO Performance Metrics: guides/yolo-performance-metrics.md
       - YOLO Thread-Safe Inference: guides/yolo-thread-safe-inference.md
+      - YOLO Data Augmentation: guides/yolo-data-augmentation.md
       - Model Deployment Options: guides/model-deployment-options.md
       - K-Fold Cross Validation: guides/kfold-cross-validation.md
       - Hyperparameter Tuning: guides/hyperparameter-tuning.md
@@ -654,7 +655,9 @@ nav:
 
 # Plugins including 301 redirects navigation ---------------------------------------------------------------------------
 plugins:
-  - macros
+  - macros:
+      include_yaml:
+        - ultralytics/cfg/default.yaml
   # - search:
   #     lang: en
   - mkdocstrings: